Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology

<p dir="ltr">We explore THz communication uplink multi-access with multi-hop Intelligent reflecting surfaces (IRSs) under correlated channels. Our aims are twofold: 1) enhancing the data rate of a desired user while dealing with interference from another user and 2) maximizing the co...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Muhammad Shehab (16904880) (author)
مؤلفون آخرون: Mohamed Elsayed (3524918) (author), Abdullateef Almohamad (16870074) (author), Ahmed Badawy (6992093) (author), Tamer Khattab (16870086) (author), Nizar Zorba (16888728) (author), Mazen Hasna (16904661) (author), Daniele Trinchero (16904886) (author)
منشور في: 2024
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513545102688256
author Muhammad Shehab (16904880)
author2 Mohamed Elsayed (3524918)
Abdullateef Almohamad (16870074)
Ahmed Badawy (6992093)
Tamer Khattab (16870086)
Nizar Zorba (16888728)
Mazen Hasna (16904661)
Daniele Trinchero (16904886)
author2_role author
author
author
author
author
author
author
author_facet Muhammad Shehab (16904880)
Mohamed Elsayed (3524918)
Abdullateef Almohamad (16870074)
Ahmed Badawy (6992093)
Tamer Khattab (16870086)
Nizar Zorba (16888728)
Mazen Hasna (16904661)
Daniele Trinchero (16904886)
author_role author
dc.creator.none.fl_str_mv Muhammad Shehab (16904880)
Mohamed Elsayed (3524918)
Abdullateef Almohamad (16870074)
Ahmed Badawy (6992093)
Tamer Khattab (16870086)
Nizar Zorba (16888728)
Mazen Hasna (16904661)
Daniele Trinchero (16904886)
dc.date.none.fl_str_mv 2024-01-23T09:00:00Z
dc.identifier.none.fl_str_mv 10.1109/ojcoms.2024.3357701
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Terahertz_Multiple_Access_A_Deep_Reinforcement_Learning_Controlled_Multihop_IRS_Topology/29445998
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Information and computing sciences
Machine learning
Artificial intelligence
multi-access communication
sub-millimeter wave communication
communication system performance
Optimization
Reflection
Wireless communication
Uplink
Propagation losses
Correlation
Array signal processing
dc.title.none.fl_str_mv Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">We explore THz communication uplink multi-access with multi-hop Intelligent reflecting surfaces (IRSs) under correlated channels. Our aims are twofold: 1) enhancing the data rate of a desired user while dealing with interference from another user and 2) maximizing the combined data rate. Both tasks involve non-convex optimization challenges. For the first aim, we devise a sub-optimal analytical approach that focuses on maximizing the desired user’s received power, leading to an over-determined system. We also attempt to use approximate solutions utilizing pseudo-inverse (P<sub><em>i</em></sub><sub><em>n</em></sub><sub><em>v</em></sub>) and block solution <i>(</i><i>B</i><i>L</i><i>S</i><i>)</i> based methods. For the second aim, we establish a loose upper bound and employ an exhaustive search <i>(</i><i>E</i><i>S</i><i>)</i> . We employ deep reinforcement learning (DRL) to address both aims, demonstrating its effectiveness in complex scenarios. DRL outperforms mathematical approaches for the first aim, with the performance improvement of DDPG over the block solution ranging from 8% to 57.12%, and over the pseudo-inverse ranging from 41% to 190% for a correlation-factor equal to 1. Moreover, DRL closely approximates the <i>E</i><i>S</i><i> </i>for the second aim. Furthermore, our findings show that as channel correlation increases, DRL’s performance improves, capitalizing on the correlation for enhanced statistical learning</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Open Journal of the Communications Society<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/ojcoms.2024.3357701" target="_blank">https://dx.doi.org/10.1109/ojcoms.2024.3357701</a></p>
eu_rights_str_mv openAccess
id Manara2_07c4949276e7764ff540ac46d0861f09
identifier_str_mv 10.1109/ojcoms.2024.3357701
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29445998
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS TopologyMuhammad Shehab (16904880)Mohamed Elsayed (3524918)Abdullateef Almohamad (16870074)Ahmed Badawy (6992093)Tamer Khattab (16870086)Nizar Zorba (16888728)Mazen Hasna (16904661)Daniele Trinchero (16904886)EngineeringElectrical engineeringInformation and computing sciencesMachine learningArtificial intelligencemulti-access communicationsub-millimeter wave communicationcommunication system performanceOptimizationReflectionWireless communicationUplinkPropagation lossesCorrelationArray signal processing<p dir="ltr">We explore THz communication uplink multi-access with multi-hop Intelligent reflecting surfaces (IRSs) under correlated channels. Our aims are twofold: 1) enhancing the data rate of a desired user while dealing with interference from another user and 2) maximizing the combined data rate. Both tasks involve non-convex optimization challenges. For the first aim, we devise a sub-optimal analytical approach that focuses on maximizing the desired user’s received power, leading to an over-determined system. We also attempt to use approximate solutions utilizing pseudo-inverse (P<sub><em>i</em></sub><sub><em>n</em></sub><sub><em>v</em></sub>) and block solution <i>(</i><i>B</i><i>L</i><i>S</i><i>)</i> based methods. For the second aim, we establish a loose upper bound and employ an exhaustive search <i>(</i><i>E</i><i>S</i><i>)</i> . We employ deep reinforcement learning (DRL) to address both aims, demonstrating its effectiveness in complex scenarios. DRL outperforms mathematical approaches for the first aim, with the performance improvement of DDPG over the block solution ranging from 8% to 57.12%, and over the pseudo-inverse ranging from 41% to 190% for a correlation-factor equal to 1. Moreover, DRL closely approximates the <i>E</i><i>S</i><i> </i>for the second aim. Furthermore, our findings show that as channel correlation increases, DRL’s performance improves, capitalizing on the correlation for enhanced statistical learning</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Open Journal of the Communications Society<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/ojcoms.2024.3357701" target="_blank">https://dx.doi.org/10.1109/ojcoms.2024.3357701</a></p>2024-01-23T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/ojcoms.2024.3357701https://figshare.com/articles/journal_contribution/Terahertz_Multiple_Access_A_Deep_Reinforcement_Learning_Controlled_Multihop_IRS_Topology/29445998CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/294459982024-01-23T09:00:00Z
spellingShingle Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology
Muhammad Shehab (16904880)
Engineering
Electrical engineering
Information and computing sciences
Machine learning
Artificial intelligence
multi-access communication
sub-millimeter wave communication
communication system performance
Optimization
Reflection
Wireless communication
Uplink
Propagation losses
Correlation
Array signal processing
status_str publishedVersion
title Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology
title_full Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology
title_fullStr Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology
title_full_unstemmed Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology
title_short Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology
title_sort Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology
topic Engineering
Electrical engineering
Information and computing sciences
Machine learning
Artificial intelligence
multi-access communication
sub-millimeter wave communication
communication system performance
Optimization
Reflection
Wireless communication
Uplink
Propagation losses
Correlation
Array signal processing